Arize AI detailed a benchmarking setup that pairs the open-source Harbor framework with its Phoenix observability platform to evaluate AI agents, MCP servers, skills, and CLIs in reproducible sandboxe…
AcruxCore launched as an open-source, Apache 2.0 platform that versions both prompts and the tools they call, runs them through a single gateway, and traces every call, tool failure and change. The co…
Waymo reported that its fully autonomous Waymo Driver was involved in 841 fewer injury-causing crashes across 270 million miles of driverless operations through the end of June 2026, an 82% reduction …
A practical guide outlines LLM observability and evaluation tooling for small teams, indie developers, and startups, covering must-have capabilities such as request/response logging, latency and token…
A Waymo driverless taxi became stuck for more than 10 minutes in an "AI loop" on a flooded Phoenix street this month, hesitating and nearly backing into another car before drivers went around it, acco…
Dynatrace acquired Arize AI to fold AI observability, evaluation and agent monitoring into its application observability platform, Dynatrace chief product officer Steve Tack and Arize AI co-founder an…
LLM-as-judge architectures are shifting from offline evaluation into agent runtime control flow, letting applications make judgment calls on AI-generated work as it happens, according to a technical a…
Elixir 1.20, released June 3, now performs whole-program type inference without annotations, catching verified bugs in production, and ElixirConf US 2026 in Chicago highlights the type system's gradua…
Seldon, an AI infrastructure company, argues that many production LLM calls are repeated behavioral contracts that cheaper models could serve, and its router and Import Audit tools aim to reconstruct …
Sanctuary AI announced on June 17 that it will license its Carbon AI control system to run on third-party robots, after achieving a 99.5% success rate on a wire-plugging task for a Tier 1 automotive s…
Sanctuary AI, a Vancouver-based robotics company, reported a 99.5% success rate across 313 wire-plugging trials in a 40-minute test for an unnamed Tier 1 automotive supplier, with a 2.54-second cycle …
A new guide from Honeycomb compares seven Datadog alternatives for AI and agent observability, highlighting cost predictability, investigation complexity, and OpenTelemetry portability as key factors.…
A developer's debugging framework for AI agent observability identifies memory state, tool execution, and retrieval validity as the three critical pillars for diagnosing failures in production. The fr…
ZizkaDB, an open-source operational database for LLM agents, introduces causal lineage and session replay features to address behavioral debugging gaps in traditional tracing tools. The database store…
Waymo's Gemini integration in its Ojai cabin is rolling out as a limited beta, not a universal feature. The company's May 2026 announcement detailed initial riders in San Francisco, Phoenix, and Los A…
Promptfoo is recommended as the primary evaluation tool for AI agents focused on documentation and RAG tasks, with Ragas and LangSmith suggested for deeper analysis. The guidance from Promptfoo, Huggi…
Linux Mint users report that firmware version 2.29 of the amdgpu DMCUB firmware breaks display output on AMD Radeon RX 6800 XT (Sienna Cichlid) GPUs, causing a half-black screen, while reverting to ve…
Waymo received final approval from the California Public Utilities Commission and the California Department of Motor Vehicles to expand its autonomous ride-hailing service to the entire Bay Area, Sacr…
X has open sourced a larger version of its For You feed ranking algorithm on GitHub under the Apache License 2.0, including configuration parameters, weights, visibility-filtering code, and label syst…
Tidewave has launched Tidewave Toolbar and Tidewave Connect, enabling developers to use Tidewave from their terminal or editor with agents like Claude Code, Codex, Cursor, or OpenCode. The new tools p…